1
0
mirror of https://github.com/osmarks/nanogpt-experiments.git synced 2024-12-24 00:50:28 +00:00
nanogpt-experiments/config/eval_gpt2_large.py

9 lines
215 B
Python
Raw Normal View History

# evaluate the base gpt2
# n_layer=36, n_head=20, n_embd=1280
# 774M parameters
batch_size = 8
eval_iters = 500 # use more iterations to get good estimate
eval_only = True
wandb_log = False
init_from = 'gpt2-large'